An evolutionary autoencoder for dynamic community detection

Wang, Zhen; Wang, Chunyu; Gao, Chao; Li, Xuelong; Li, Xianghua

doi:10.1007/s11432-020-2827-9

Cited by 34 publications

(13 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To discover time-varying dynamic community structure, Semi-supervised Evolutionary Autoencoder (sE-Autoencoder) [96] is developed within an evolutionary clustering framework, assuming community structures at previous time steps successively guide the detection at the current time step. To this end, sE-Autoencoder adds a temporal smoothness regularization L(Z (t) , Z (t−1) ) into the objective function in [92] for minimization:…”

Section: A Stacked Ae-based Community Detectionmentioning

confidence: 99%

“…Re-training over static network snapshots is not an ideal solution. In our literature review, only one study touches the topic by designing an evolutionary AE aiming at discovering smoothly changing community structure over snapshots [96]. Technical challenges in detecting a dynamic network focus on controlling the dynamics (i.e., spatial and temporal properties) in the model training process.…”

Section: K Dynamic Networkmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Survey on Community Detection With Deep Learning

Xue

Liu

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

213

View full text Add to dashboard Cite

A community reveals the features and connections of its members that are different from those in other communities in a network. Detecting communities is of great significance in network analysis. Despite the classical spectral clustering and statistical inference methods, we notice a significant development of deep learning techniques for community detection in recent years with their advantages in handling high dimensional network data. Hence, a comprehensive overview of community detection's latest progress through deep learning is timely to both academics and practitioners. This survey devises and proposes a new taxonomy covering different categories of the state-of-theart methods, including deep learning-based models upon deep neural networks, deep nonnegative matrix factorization and deep sparse filtering. The main category, i.e., deep neural networks, is further divided into convolutional networks, graph attention networks, generative adversarial networks and autoencoders. The survey also summarizes the popular benchmark data sets, model evaluation metrics, and open-source implementations to address experimentation settings. We then discuss the practical applications of community detection in various domains and point to implementation scenarios. Finally, we outline future directions by suggesting challenging topics in this fast-growing deep learning field.

show abstract

Section: A Stacked Ae-based Community Detectionmentioning

confidence: 99%

Section: K Dynamic Networkmentioning

confidence: 99%

A Comprehensive Survey on Community Detection With Deep Learning

Xue

Liu

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

213

View full text Add to dashboard Cite

show abstract

“…In recommender systems, many classic collaborative filtering algorithms fall into the class of matrix factorization (MF) [28]. MF-based models project users and items into a low-dimensional latent space and represent a user or an item by a vector [29]. The inner product of a user vector and an item vector represents the user's satisfaction degree to the item.…”

Section: Mf-based Recommendationmentioning

confidence: 99%

Contrastive Graph Learning for Social Recommendation

Zhang

Huang

et al. 2022

Front. Phys.

View full text Add to dashboard Cite

Owing to the strength in learning representation of the high-order connectivity of graph neural networks (GNN), GNN-based collaborative filtering has been widely adopted in recommender systems. Furthermore, to overcome the data sparsity problem, some recent GNN-based models attempt to incorporate social information and to design contrastive learning as an auxiliary task to assist the primary recommendation task. Existing GNN and contrastive-learning-based recommendation models learn user and item representations in a symmetrical way and utilize social information and contrastive learning in a complex manner. The above two strategies lead to these models being either ineffective for datasets with a serious imbalance between users and items or inefficient for datasets with too many users and items. In this work, we propose a contrastive graph learning (CGL) model, which combines social information and contrastive learning in a simple and powerful way. CGL consists of three modules: diffusion, readout, and prediction. The diffusion module recursively aggregates and integrates social information and interest information to learn representations of users and items. The readout module takes the average value of user embeddings from all diffusion layers and item embeddings at the last diffusion layer as readouts of users and items, respectively. The prediction module calculates prediction rating scores with an interest graph to emphasize interest information. Three different losses are designed to ensure the function of each module. Extensive experiments on three benchmark datasets are implemented to validate the effectiveness of our model.

show abstract

“…Similarly, Wu et al [14] explored the impact of three different kinds of awareness on the epidemic spread in a scale-free networked population. However, single-layer networks provide a limited representation of complex systems [15][16][17]. The efforts in [13,14] may fail to involve the realistic scenario where the information and virus spread via different networks simultaneously.…”

Section: Introductionmentioning

confidence: 99%

The impact of information dissemination on vaccination in multiplex networks

Liu

2022

Sci. China Inf. Sci.

View full text Add to dashboard Cite

The impact of information dissemination on epidemic control is essentially subject to individual behaviors. Vaccination is one of the most effective strategies against the epidemic spread, whose correlation with the information dissemination should be better understood. To this end, we propose an evolutionary vaccination game model in multiplex networks by integrating an information-epidemic spreading process into the vaccination dynamics, and explore how information dissemination influences vaccination. The spreading process is described by a two-layer coupled susceptible-alert-infected-susceptible (SAIS) model, where the strength coefficient between two layers characterizes the tendency and intensity of information dissemination. We find that the impact of information dissemination on vaccination decision-making depends on not only the vaccination cost and network topology, but also the stage of the system evolution. For instance, in a two-layer BA scale-free network, information dissemination helps to improve vaccination density only at the early stage of the system evolution, as well as when the vaccination cost is smaller. A counter-intuitive conclusion that more information transmission cannot promote vaccination is obtained when the vaccination cost is larger. Moreover, we study the impact of the strength coefficient and individual sensitivity on the fraction of infected individuals and social cost, and unveil the role of information dissemination in controlling the epidemic.

show abstract

An evolutionary autoencoder for dynamic community detection

Cited by 34 publications

References 42 publications

A Comprehensive Survey on Community Detection With Deep Learning

A Comprehensive Survey on Community Detection With Deep Learning

Contrastive Graph Learning for Social Recommendation

The impact of information dissemination on vaccination in multiplex networks

Contact Info

Product

Resources

About